# Ranked List Loss for Deep Metric Learning

arXiv: https://arxiv.org/abs/1903.03238 · HTML: https://mlsanity.com/paper/1903.03238/

## Key facts

- Cited by 77 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Mar 2019.

## Built on by (most cited first, 30 of 77)

- [Self-Attention Between Datapoints: Going Beyond Individual Input-Output Pairs in Deep Learning](https://mlsanity.com/paper/2106.02584/) (2021)
- [Use All The Labels: A Hierarchical Multi-Label Contrastive Learning Framework](https://mlsanity.com/paper/2204.13207/) (2022)
- [Farewell to Mutual Information: Variational Distillation for Cross-Modal Person Re-Identification](https://mlsanity.com/paper/2104.02862/) (2021)
- [Eliminate Deviation with Deviation for Data Augmentation and a General Multi-modal Data Learning Method](https://mlsanity.com/paper/2101.08533/) (2021)
- [von Mises-Fisher Loss: An Exploration of Embedding Geometries for Supervised Learning](https://mlsanity.com/paper/2103.15718/) (2021)
- [Mutual Contrastive Learning for Visual Representation Learning](https://mlsanity.com/paper/2104.12565/) (2021)
- [Unbiased Supervised Contrastive Learning](https://mlsanity.com/paper/2211.05568/) (2022)
- [Learning Intra-Batch Connections for Deep Metric Learning](https://mlsanity.com/paper/2102.07753/) (2021)
- [Beyond Just Vision: A Review on Self-Supervised Representation Learning on Multimodal and Temporal Data](https://mlsanity.com/paper/2206.02353/) (2022)
- [HIER: Metric Learning Beyond Class Labels via Hierarchical Regularization](https://mlsanity.com/paper/2212.14258/) (2022)
- [Noise-resistant Deep Metric Learning with Ranking-based Instance Selection](https://mlsanity.com/paper/2103.16047/) (2021)
- [SphereFace Revived: Unifying Hyperspherical Face Recognition](https://mlsanity.com/paper/2109.05565/) (2021)
- [Deep Relational Metric Learning](https://mlsanity.com/paper/2108.10026/) (2021)
- [Learning with Memory-based Virtual Classes for Deep Metric Learning](https://mlsanity.com/paper/2103.16940/) (2021)
- [COCOA: Cross Modality Contrastive Learning for Sensor Data](https://mlsanity.com/paper/2208.00467/) (2022)
- [Adaptive Sparse Pairwise Loss for Object Re-Identification](https://mlsanity.com/paper/2303.18247/) (2023)
- [Proxy Synthesis: Learning with Synthetic Classes for Deep Metric Learning](https://mlsanity.com/paper/2103.15454/) (2021)
- [MIN2Net: End-to-End Multi-Task Learning for Subject-Independent Motor Imagery EEG Classification](https://mlsanity.com/paper/2102.03814/) (2021)
- [Proxy Anchor-based Unsupervised Learning for Continuous Generalized Category Discovery](https://mlsanity.com/paper/2307.10943/) (2023)
- [Segment Anything Model is a Good Teacher for Local Feature Learning](https://mlsanity.com/paper/2309.16992/) (2023)
- [Generalizing and Decoupling Neural Collapse via Hyperspherical Uniformity Gap](https://mlsanity.com/paper/2303.06484/) (2023)
- [Informative and Representative Triplet Selection for Multilabel Remote Sensing Image Retrieval](https://mlsanity.com/paper/2105.03647/) (2021)
- [A Comprehensive Survey on Deep-Learning-based Vehicle Re-Identification: Models, Data Sets and Challenges](https://mlsanity.com/paper/2401.10643/) (2024)
- [Adaptive Hierarchical Similarity Metric Learning with Noisy Labels](https://mlsanity.com/paper/2111.00006/) (2021)
- [Contrastive Bayesian Analysis for Deep Metric Learning](https://mlsanity.com/paper/2210.04402/) (2022)
- [RankDNN: Learning to Rank for Few-shot Learning](https://mlsanity.com/paper/2211.15320/) (2022)
- [Anomaly Detection with Score Distribution Discrimination](https://mlsanity.com/paper/2306.14403/) (2023)
- [Introspective Deep Metric Learning](https://mlsanity.com/paper/2309.09982/) (2023)
- [Multi-level Distance Regularization for Deep Metric Learning](https://mlsanity.com/paper/2102.04223/) (2021)
- [The Group Loss++: A deeper look into group loss for deep metric learning](https://mlsanity.com/paper/2204.01509/) (2022)

## Abstract (arXiv)

The objective of deep metric learning (DML) is to learn embeddings that can capture semantic similarity and dissimilarity information among data points. Existing pairwise or tripletwise loss functions used in DML are known to suffer from slow convergence due to a large proportion of trivial pairs or triplets as the model improves. To improve this, ranking-motivated structured losses are proposed recently to incorporate multiple examples and exploit the structured information among them. They converge faster and achieve state-of-the-art performance. In this work, we unveil two limitations of existing ranking-motivated structured losses and propose a novel ranked list loss to solve both of them. First, given a query, only a fraction of data points is incorporated to build the similarity structure. Consequently, some useful examples are ignored and the structure is less informative. To address this, we propose to build a set-based similarity structure by exploiting all instances in the gallery. The learning setting can be interpreted as few-shot retrieval: given a mini-batch, every example is iteratively used as a query, and the rest ones compose the gallery to search, i.e., the support set in few-shot setting. The rest examples are split into a positive set and a negative set. For every mini-batch, the learning objective of ranked list loss is to make the query closer to the positive set than to the negative set by a margin. Second, previous methods aim to pull positive pairs as close as possible in the embedding space. As a result, the intraclass data distribution tends to be extremely compressed. In contrast, we propose to learn a hypersphere for each class in order to preserve useful similarity structure inside it, which functions as regularisation. Extensive experiments demonstrate the superiority of our proposal by comparing with the state-of-the-art methods.